WO2013121321A1 - Method for quantification of uncertainty of contours in manual & auto segmenting algorithms - Google Patents
Method for quantification of uncertainty of contours in manual & auto segmenting algorithms Download PDFInfo
- Publication number
- WO2013121321A1 WO2013121321A1 PCT/IB2013/050952 IB2013050952W WO2013121321A1 WO 2013121321 A1 WO2013121321 A1 WO 2013121321A1 IB 2013050952 W IB2013050952 W IB 2013050952W WO 2013121321 A1 WO2013121321 A1 WO 2013121321A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- region
- uncertainty
- sub
- boundary
- ooi
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20116—Active contour; Active surface; Snakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Definitions
- the present application relates generally to image processing. It finds particular application in conjunction with segmenting medical images and will be described with particular reference thereto. However, it is to be understood that it also finds application in other usage scenarios and is not necessarily limited to the aforementioned application.
- the grade and intensity of a lesion is an important factor in determining a diagnosis and available treatment options for the patient.
- the grade and intesity of a lesion is determined by assessing images of the lesion.
- Nuclear medical imaging modalities are the primary imaging modality for generating the images.
- lesion delineation is an important step for correctly determining the grade and intensity of the lesion.
- lesion delineation can be challenging.
- a low confidence in the lesion boundary is not necessarily a disadvantage.
- Physicians use the irregular and imprecise nature of the boundary as an important characteristic of tumors which distinguishes tumors from benign lesions.
- tumor boundary irregularity can be used to distinguish between active tuberculosis nodules and malignant lesions (both of which have high metabolism and take up fluorodeoxyglucose (FDG) in positron emission tomography (PET) preferentially).
- FDG fluorodeoxyglucose
- PET positron emission tomography
- the present application provides new and improved methods and systems which overcome the above-referenced challenges and others.
- a system for quantification of uncertainty of contours includes a processor programmed to receive an image including an object of interest (OOI). Further, a band of uncertainty delineating a region in the received image is received. The region includes the boundary of the OOI. For each of a plurality of sub-regions of the region, a determination as to whether to filter the sub-region is made. The determination including at least one of determining whether the boundary of the OOI can be delineated in the sub-region with a confidence level exceeding a first
- Another advantage resides in filtering sub-regions to a different extent based on a confidence level.
- Another advantage resides in indicating accuracy of a part of or the entire identified boundary.
- the invention may take form in various components and arrangements of components, and in various steps and arrangements of steps.
- the drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
- FIGURE 1 illustrates a block diagram of a system for quantifying uncertainty of contours in manual and auto segmenting algorithms.
- FIGURE 2 illustrates a positron emission tomography (PET) image of a patient with malignant lesions in the lung.
- PET positron emission tomography
- FIGURE 3 illustrates a zoomed axial view of the PET image of
- FIGURE 2 is a diagrammatic representation of FIGURE 1
- FIGURES 4 and 5 illustrate a block diagram of a method for delineating an object of interest in a image.
- a therapy system 10 includes one or more imaging modalities 12 for acquiring images of objects of interest, such as legions, within patients.
- the imaging modalities 12 suitably include one or more of a computed tomography (CT) scanner, a positron emission tomography (PET) scanner, a magnetic resonance (MR) scanner, a single photon emission computed tomography (SPECT) scanner, a cone-beam computed tomography (CBCT) scanner, and the like.
- CT computed tomography
- PET positron emission tomography
- MR magnetic resonance
- SPECT single photon emission computed tomography
- CBCT cone-beam computed tomography
- a segmentation device 16 receives an image 18, such as a three- and/or four- dimensional image, of an object of interest (OOI) 20, such as a lesion, an example of which is shown in FIGURES 2 and 3.
- the received image 18 can, for example, be a Dynamic Contrast Enhanced MR image.
- the image 18 is received from the imaging modalities 12 and/or the image memories 14.
- the image 18 can be received from the imaging modalities 12 through the image memories 14.
- other sources for the image 18 are contemplated.
- the image 18 is typically received from nuclear imaging modalities.
- the segmentation device 16 delineates the OOI 20 in the received image 18. If the received image 18 is four-dimensional, the OOI 20 is delineated in all phases of the received image 18.
- a user interface thereof is displayed on a display device 24 of the segmentation device 16.
- the user interface suitably allows an associated user to view the received image 18.
- the user interface allows the associated user to create and/or modify contours 26, 28 on the received imaged 18 using a user input device 30 of the of the segmentation device 16.
- a contour specifies the boundary of a region, such as a lesion, in a two-dimensional image space.
- the associated user can, for example, employ a mouse to draw a contour on the received image 18 and/or resize a contour on the received image 18.
- the user interface further allows the associated user to specify parameters for segmentation using the user input device 30.
- the segmentation application 22 employs a method 50 of FIGURE 4.
- a band of uncertainty 32 is received 52 for the received image 18.
- the band of uncertainty 32 is defined by an outer contour 26 and an inner contour 28, which collectively identify a region 34 within which the boundary of the OOI 20 is expected.
- the region 34 typically includes a portion of the received image 18, but can also include the entire image.
- the outer contour 26 marks a region within which the boundary of the OOI 20 is, and the inner contour 28 marks a region outside of which the boundary of the OOI 20 is.
- the associated user draws the band of uncertainty 32 using the user interface such that the inner contour 28 and the outer contour 26 are received from the user input device 30.
- the band of uncertainty 32 can be received from other sources.
- the band of uncertainty 32 can be received from an algorithm for automatically determining the band of uncertainty 32.
- the boundary is delineated 54 in the region 34 or the sub-region and a confidence level or a metric of uncertainty is determined 54 for the region 34 or the sub-region.
- the sub-regions each span from the inner contour 28 to the outer contour 26. Further, the sub-regions can at least partially be identified by the associated user using the user interface. Additionally or alternatively, the sub-regions can at least partially be identified using an algorithm. For example, the band of uncertainty 32 can be broken into a predetermined number of sub-regions of equal area. The sub-regions can be processed sequentially and/or in parallel.
- a determination 56 is made as to whether it is possible to determine the boundary of the OOI 20 in the region 34 or the sub-region.
- the determination 56 can be performed manually and/or automatically.
- the manual determination can be made by the associated user through receipt of data from the user input device 30.
- the associated user can view the received image 18 using the user interface to make the determination.
- the boundary can be manually determined with confidence if the boundary points can be visually delineated in the received image 18.
- an algorithm can be employed to assess whether it is possible to determine the boundary of the OOI 20 in the region 34 or the sub-region with confidence.
- the boundary can be
- the boundary is manually and/or automatically delineated 58 in the received image 18.
- the user interface can be employed to allow the associated user to draw at least part of a contour around the OOI 20 of the region or the sub-region.
- an algorithm can be employed. If it is not possible to manually and/or automatically determine the boundary of the OOI 20 in the region 34 or the sub-region with confidence, a determination 60 is made as to whether a stopping condition is met.
- a stopping condition indicates that enhancement of the region 34 or the sub- region is of no value.
- the stopping condition can be, for example, a predetermined number of iterations, discussed below, a confidence level of the boundary being less than a
- the associated user can delineate 56 the boundary of the OOI 20 in the region 34 or the sub-region using another image and, optionally, register the other image to the received image 18. Additionally, or alternatively, the boundary of the OOI 20 in the region 34 or the sub-region can be delineated 56 in the received image 18 along the midline of the region 34 or the sub-region.
- a filtering algorithm for enhancing edges is then iteratively run 62 in the region 34 or the sub-region for a predetermined number of iterations, such as five iterations, and the determination 56 is repeated.
- the filtering algorithm is a stochastic scale space algorithm, but any filtering algorithm can be employed.
- the predetermined number of iterations is suitably determined by the associated user and/or an administrator of the segmentation device 16. Further, the predetermined number is the number of iterations the one determining the predetermined number deems to be sufficient to achieve a noticeable enhancement to the region 34 or the sub-region.
- FIGURE 6 illustrates several images where the edge is strengthened to an extent that it can be subsequently delineated just by thresholding.
- FIGURE 6A shows the original image
- FIGURE 6B shows the original image after 50 iterations of the filtering algorithm
- FIGURE 6C shows the original image after 100 iterations of the filtering algorithm
- FIGURE 6D shows the original image after 200 iterations of the filtering algorithm.
- FIGURE 6 illustrates the progression of edge enhancement for an increasing number of iterations.
- the filtering of the region 34 can be done only across the boundary (i.e., the direction perpendicular to the boundary direction).
- the region 34 of the band of uncertainty 32 can be divided into the plurality of sub-regions, one for each point within the band of uncertainty 32 (hereafter referred to as a point of uncertainty).
- the sub-region for a point of uncertainty 36 is defined by all the points along an outer line segment 38 and inner line segment 40, examples of which are illustrated in FIGURE 7, of the point of uncertainty 36.
- the outer line segment 38 is determined by joining the point of uncertainty 36 with its projection on the outer contour 26
- the inner line segment 40 is determined by joining the point of uncertainty 36 with its projection on the inner contour 28.
- the projection of the point of uncertainty 36 on the outer contour 26 is the point on the outer contour 26 which is closest to the point of uncertainty 36
- the projection of the point of uncertainty 36 on the inner contour 28 is the point on the inner contour 28 which is closest to the point of uncertainty 36.
- the plurality of sub-regions includes overlapping sub-regions.
- a confidence level or a metric of uncertainty is determined 64 for the region 34 or the sub-region.
- the confidence level and the metric of uncertainty are based on the extent of filtering needed to determine the boundary. Further, the metric of uncertainty and the confidence level are inversely related. For example, as the number of filtering iterations increase, the uncertainty increases and the confidence level decreases. Hence, the confidence level can be determined from the metric of uncertainty and vice versa.
- uncertainty for the region 34 or the sub-region can be determined as follows. If the boundary of the region 34 or the sub-region was drawn with confidence without any filtering, an uncertainly value of 0 can be assigned to the region 34 or the sub-region. If the boundary was determined at the nth iteration, a value between 0 and
- x is the number of iterations and F(x ⁇ is strength gradient of the region 34 or the sub- region.
- F(x ⁇ ) is strength gradient of the region 34 or the sub- region.
- the region 34 or the sub-region can be assigned a maximum uncertainty value (e.g., 100).
- Confidence can then be defined as the additive inverse of Uncertainty with respect to 100. In other words, confidence can be defined as follows:
- clinicians can diagnose a patient and determine the best treatment options.
- Clinicians use the irregular and imprecise nature of the boundary as an important characteristic of tumors, which distinguishes them from benign lesions.
- tumor boundary irregularity can be used to distinguish between active tuberculosis nodules and malignant lesions.
- Confidence level and/or metric of uncertainty can be employed to determine whether a boundary is irregular and imprecise.
- the confidence of the final diagnosis can be determined based on confidence level and/or metric of uncertainty of the segmentation. More conservative treatment options can be employed when, for example, the confidence in the final diagnosis is low.
- the segmentation device 16 include at least one processor 42 executing computer executable instructions on at least one memory 44 thereof.
- the computer executable instructions carry out the functionality of the segmentation device 16 and include the segmentation application 22.
- the segmentation device 16 can include a communication unit 46 and/or at least one system bus 48.
- the communications unit 46 provides the processor 42 with an interface to at least one communication network.
- the communications unit 46 can, for example, be employed to communicate with the imaging modalities 12 and/or the image memories 14.
- the system bus 48 allows the exchange of data between the display device 24, the user input device 30, the processor 42, the memory 44 and the communication unit 46.
- a memory includes one or more of a non-transient computer readable medium; a magnetic disk or other magnetic storage medium; an optical disk or other optical storage medium; a random access memory (RAM), read-only memory (ROM), or other electronic memory device or chip or set of operatively interconnected chips; an
- a processor includes one or more of a microprocessor, a microcontroller, a graphic processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and the like;
- a user input device includes one or more of a mouse, a keyboard, a touch screen display, one or more buttons, one or more switches, one or more toggles, and the like;
- a database includes one or more memories; and
- a display device includes one or more of a LCD display, an LED display, a plasma display, a projection display, a touch screen display, and the like.
Abstract
Description
Claims
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112014019791A BR112014019791A8 (en) | 2012-02-14 | 2013-02-05 | SYSTEM FOR THE QUANTIFICATION OF CONTOUR UNCERTAINTY, METHOD FOR THE QUANTIFICATION OF CONTOUR UNCERTAINTY, AT LEAST ONE PROCESSOR AND NON-TRANSITORY COMPUTER READABLE MEDIUM |
US14/375,836 US10460448B2 (en) | 2012-02-14 | 2013-02-05 | Method for quantification of uncertainty of contours in manual and auto segmenting algorithms |
EP13711967.3A EP2815382B1 (en) | 2012-02-14 | 2013-02-05 | Method for quantification of uncertainty of contours in manual and auto segmenting algorithms |
RU2014137155A RU2014137155A (en) | 2012-02-14 | 2013-02-05 | METHOD FOR QUANTITATIVE ASSESSMENT OF UNCERTAINTY OF CIRCUITS IN MANUAL AND AUTOMATIC SEGMENTATION ALGORITHMS |
CN201380009392.1A CN104115191B (en) | 2012-02-14 | 2013-02-05 | Quantify the system of the uncertainty of profile with manual & automatic segmentation algorithms |
US16/576,971 US20200013171A1 (en) | 2012-02-14 | 2019-09-20 | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201261598368P | 2012-02-14 | 2012-02-14 | |
US61/598,368 | 2012-02-14 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/375,836 A-371-Of-International US10460448B2 (en) | 2012-02-14 | 2013-02-05 | Method for quantification of uncertainty of contours in manual and auto segmenting algorithms |
US16/576,971 Continuation US20200013171A1 (en) | 2012-02-14 | 2019-09-20 | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013121321A1 true WO2013121321A1 (en) | 2013-08-22 |
Family
ID=47997624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2013/050952 WO2013121321A1 (en) | 2012-02-14 | 2013-02-05 | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms |
Country Status (6)
Country | Link |
---|---|
US (2) | US10460448B2 (en) |
EP (1) | EP2815382B1 (en) |
CN (1) | CN104115191B (en) |
BR (1) | BR112014019791A8 (en) |
RU (1) | RU2014137155A (en) |
WO (1) | WO2013121321A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220301177A1 (en) * | 2019-08-16 | 2022-09-22 | Siemens Healthcare Gmbh | Updating boundary segmentations |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100104513A1 (en) * | 2008-10-28 | 2010-04-29 | General Electric Company | Method and system for dye assessment |
US20120075638A1 (en) * | 2010-08-02 | 2012-03-29 | Case Western Reserve University | Segmentation and quantification for intravascular optical coherence tomography images |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1996016534A2 (en) * | 1994-11-25 | 1996-06-06 | Sophisview Technologies, Ltd. | System and method for diagnosis of living tissue diseases |
US7038697B2 (en) * | 2003-02-25 | 2006-05-02 | Microsoft Corporation | Color gradient paths |
EP1603076A1 (en) * | 2004-05-13 | 2005-12-07 | Aalborg Universitet | Computerized cortex boundary extraction from MR images |
US7804989B2 (en) * | 2006-10-30 | 2010-09-28 | Eigen, Inc. | Object recognition system for medical imaging |
US9730663B2 (en) | 2007-08-31 | 2017-08-15 | Koninklijke Philips N.V. | Uncertainty maps for segmentation in the presence of metal artifacts |
US8094896B2 (en) * | 2008-04-14 | 2012-01-10 | General Electric Company | Systems, methods and apparatus for detection of organ wall thickness and cross-section color-coding |
CN101833750A (en) * | 2010-04-15 | 2010-09-15 | 清华大学 | Active contour method based on shape constraint and direction field, and system thereof |
DE102010022307A1 (en) | 2010-06-01 | 2011-12-01 | Siemens Aktiengesellschaft | Method for checking segmentation of structure e.g. left kidney in medical image data, involves performing spatially resolved automatic determination of confidence values for positions on segmentation contour using property values |
EP2878338B1 (en) * | 2013-11-28 | 2018-04-11 | RaySearch Laboratories AB | Method and system for uncertainty based radiotherapy treatment planning |
-
2013
- 2013-02-05 US US14/375,836 patent/US10460448B2/en not_active Expired - Fee Related
- 2013-02-05 EP EP13711967.3A patent/EP2815382B1/en active Active
- 2013-02-05 RU RU2014137155A patent/RU2014137155A/en not_active Application Discontinuation
- 2013-02-05 CN CN201380009392.1A patent/CN104115191B/en not_active Expired - Fee Related
- 2013-02-05 BR BR112014019791A patent/BR112014019791A8/en not_active IP Right Cessation
- 2013-02-05 WO PCT/IB2013/050952 patent/WO2013121321A1/en active Application Filing
-
2019
- 2019-09-20 US US16/576,971 patent/US20200013171A1/en not_active Abandoned
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100104513A1 (en) * | 2008-10-28 | 2010-04-29 | General Electric Company | Method and system for dye assessment |
US20120075638A1 (en) * | 2010-08-02 | 2012-03-29 | Case Western Reserve University | Segmentation and quantification for intravascular optical coherence tomography images |
Non-Patent Citations (3)
Title |
---|
RAY SHONKET ET AL: "Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics", MEDICAL PHYSICS, AIP, MELVILLE, NY, US, vol. 35, no. 12, 24 November 2008 (2008-11-24), pages 5869 - 5881, XP012115878, ISSN: 0094-2405, ISBN: 978-1-930524-56-9, DOI: 10.1118/1.3013561 * |
SHEN ET AL: "Computer Aided Classification System for Breast Ultrasound Based on Breast Imaging Reporting and Data System (BI-RADS)", ULTRASOUND IN MEDICINE AND BIOLOGY, NEW YORK, NY, US, vol. 33, no. 11, 26 October 2007 (2007-10-26), pages 1688 - 1698, XP022317512, ISSN: 0301-5629, DOI: 10.1016/J.ULTRASMEDBIO.2006.08.017 * |
XI ZHAO ET AL: "Quantification of Extensional Uncertainty of Segmented Image Objects by Random Sets", IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, IEEE SERVICE CENTER, PISCATAWAY, NJ, US, vol. 49, no. 7, 1 July 2011 (2011-07-01), pages 2548 - 2557, XP011478293, ISSN: 0196-2892, DOI: 10.1109/TGRS.2011.2109064 * |
Also Published As
Publication number | Publication date |
---|---|
EP2815382A1 (en) | 2014-12-24 |
RU2014137155A (en) | 2016-04-10 |
US10460448B2 (en) | 2019-10-29 |
BR112014019791A8 (en) | 2017-07-11 |
US20200013171A1 (en) | 2020-01-09 |
US20150043797A1 (en) | 2015-02-12 |
BR112014019791A2 (en) | 2017-06-20 |
CN104115191B (en) | 2018-11-09 |
EP2815382B1 (en) | 2022-01-19 |
CN104115191A (en) | 2014-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2413245C2 (en) | Processing positron emission tomography images using anatomic list mode mask | |
US9324167B2 (en) | Apparatus and method for generating an attenuation correction map | |
US10453198B2 (en) | Device and method for delineating a metal object for artifact reduction in tomography images | |
JP6042879B2 (en) | Apparatus for generating an assignment between an image region and an element class of an image | |
US7457448B2 (en) | Method and system for wavelet based detection of colon polyps | |
US20070248254A1 (en) | System and Method for Automatic Detection of Internal Structures in Medical Images | |
US11763454B2 (en) | Processing a medical image | |
US11594005B2 (en) | System, method and apparatus for assisting a determination of medical images | |
US9317926B2 (en) | Automatic spinal canal segmentation using cascaded random walks | |
US10062167B2 (en) | Estimated local rigid regions from dense deformation in subtraction | |
US7835555B2 (en) | System and method for airway detection | |
US10402970B2 (en) | Model-based segmentation of an anatomical structure | |
JP7278224B2 (en) | Quantified aspects of lesions in medical images | |
US20200013171A1 (en) | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms | |
US20140341452A1 (en) | System and method for efficient assessment of lesion development | |
Myint et al. | Effective kidney segmentation using gradient based approach in abdominal CT images | |
JP7321671B2 (en) | Information processing device, information processing method, information processing system and program | |
CN109564685B (en) | Robust lobe segmentation | |
US11704795B2 (en) | Quality-driven image processing | |
JP2009502430A (en) | System and method for automatically segmenting blood vessels in a chest magnetic resonance sequence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13711967 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013711967 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14375836 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014137155 Country of ref document: RU |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112014019791 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112014019791 Country of ref document: BR Kind code of ref document: A2 Effective date: 20140811 |